Divergence

Tutorials

Check out this tutorial to begin using the Divergence class

Divergence Tutorial

How To Guides

There are currently no how to’s for Divergence. If there are scenarios that you want us to explain, contact us!

DataEval API

class dataeval.metrics.Divergence(data_a: ndarray, data_b: ndarray, method: Literal['MST', 'FNN'] = 'MST')

Calculates the estimated divergence between two datasets

Parameters:

  • data_a (np.ndarray) – Array of images or image embeddings to compare

  • data_b (np.ndarray) – Array of images or image embeddings to compare

  • method (Literal["MST, "FNN"], default "MST") – Method used to estimate dataset divergence

Warning

MST is very slow in this implementation, this is unlike matlab where they have comparable speeds Overall, MST takes ~25x LONGER!! Source of slowdown: conversion to and from CSR format adds ~10% of the time diff between 1nn and scipy mst function the remaining 90%

evaluate() → Dict[str, Any]

Calculates the divergence and any errors between the datasets

Returns:

dpfloat

divergence value between 0.0 and 1.0

errorsint

the number of differing edges

Return type:

Dict[str, Any]